Modeling Variation in Human Feedback with User Inputs: An Exploratory Methodology

To expedite the development process of interactive reinforcement learning (IntRL) algorithms, prior work often uses perfect oracles as simulated human teachers to furnish feedback signals. These oracles typically derive from ground-truth knowledge or optimal policies, providing dense and error-free...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2024 19th ACM/IEEE International Conference on Human-Robot Interaction (HRI) S. 303 - 312
Hauptverfasser:	Huang, Jindan, Aronson, Reuben M., Short, Elaine Schaertl
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	ACM 11.03.2024
Schlagworte:	Behavioral sciences Computational modeling human behavior modeling Human computer interaction human feedback human-centered robotics Human-robot interaction interactive robot learning Refining Reinforcement learning Social computing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!